Pith. sign in

Taming the monster: A fast and simple algorithm for contextual bandits

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Regret-Free Reinforcement Learning for LTL Specifications

cs.AI · 2024-11-18 · conditional · novelty 6.0

A regret-free (sublinear-regret) episodic algorithm for LTL objectives, built on optimistic interval-MDP value iteration for reach-avoid and a graph-learning preprocess requiring a known minimum transition probability.

citing papers explorer

Showing 1 of 1 citing paper.

  • Regret-Free Reinforcement Learning for LTL Specifications cs.AI · 2024-11-18 · conditional · none · ref 1

    A regret-free (sublinear-regret) episodic algorithm for LTL objectives, built on optimistic interval-MDP value iteration for reach-avoid and a graph-learning preprocess requiring a known minimum transition probability.